Home▸AI & Machine Learning▸Core-Set Selection: Greedy k-Center Active Learning

Core-Set Selection: Greedy k-Center Active Learning

Interactive 3D core-set selection simulator: watch the greedy k-center algorithm pick a diverse, representative labeling batch from an unlabeled point cloud, and compare its coverage radius against random sampling at the same label budget.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted

Uncertainty sampling asks a model which points confuse it most; core-set selection asks a completely different question — which small labeled set best covers the whole feature space? This simulator renders an unlabeled point cloud embedded in a 2D feature plane and runs the real greedy k-center algorithm live in 3D: each step it measures every unlabeled point's distance to the nearest already-labeled point, picks the point that is farthest from all of them, and adds it to the labeled batch. Coverage rings shrink round by round as the covering radius drops, live readouts track the exact radius and the size of the next improvement, and a random-sampling baseline — averaged over several trials at the same label budget — is computed alongside it so you can see numerically how much tighter greedy diversity sampling covers the space than picking labels blindly.

⚙ Under the hood

Watch the greedy k-center algorithm build a diverse labeling batch by always picking the unlabeled point farthest from every already-labeled point, then compare its shrinking coverage radius against a random-sampling baseline at the same label budget.

active learningcore-set selectionk-centerdiversity samplingmachine learningdata labeling

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install